Leveraging Large Language Models for Information Verification -- an Engineering Approach

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hung, Nguyen Nang, Trong, Nguyen Thanh, Toan, Vuong Thanh, Phuoc, Nguyen An, Tu, Dao Minh, Tuan, Nguyen Manh Duc, Mau, Nguyen Dinh
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908416743571456
author Hung, Nguyen Nang
Trong, Nguyen Thanh
Toan, Vuong Thanh
Phuoc, Nguyen An
Tu, Dao Minh
Tuan, Nguyen Manh Duc
Mau, Nguyen Dinh
author_facet Hung, Nguyen Nang
Trong, Nguyen Thanh
Toan, Vuong Thanh
Phuoc, Nguyen An
Tu, Dao Minh
Tuan, Nguyen Manh Duc
Mau, Nguyen Dinh
contents For the ACMMM25 challenge, we present a practical engineering approach to multimedia news source verification, utilizing Large Language Models (LLMs) like GPT-4o as the backbone of our pipeline. Our method processes images and videos through a streamlined sequence of steps: First, we generate metadata using general-purpose queries via Google tools, capturing relevant content and links. Multimedia data is then segmented, cleaned, and converted into frames, from which we select the top-K most informative frames. These frames are cross-referenced with metadata to identify consensus or discrepancies. Additionally, audio transcripts are extracted for further verification. Noticeably, the entire pipeline is automated using GPT-4o through prompt engineering, with human intervention limited to final validation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18274
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Large Language Models for Information Verification -- an Engineering Approach
Hung, Nguyen Nang
Trong, Nguyen Thanh
Toan, Vuong Thanh
Phuoc, Nguyen An
Tu, Dao Minh
Tuan, Nguyen Manh Duc
Mau, Nguyen Dinh
Machine Learning
For the ACMMM25 challenge, we present a practical engineering approach to multimedia news source verification, utilizing Large Language Models (LLMs) like GPT-4o as the backbone of our pipeline. Our method processes images and videos through a streamlined sequence of steps: First, we generate metadata using general-purpose queries via Google tools, capturing relevant content and links. Multimedia data is then segmented, cleaned, and converted into frames, from which we select the top-K most informative frames. These frames are cross-referenced with metadata to identify consensus or discrepancies. Additionally, audio transcripts are extracted for further verification. Noticeably, the entire pipeline is automated using GPT-4o through prompt engineering, with human intervention limited to final validation.
title Leveraging Large Language Models for Information Verification -- an Engineering Approach
topic Machine Learning
url https://arxiv.org/abs/2506.18274